Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d62e88195e4e0fd449385d418b08233e5cc798826e009f134a1183e3aa2b1a
+oid sha256:fcd0d59a784934327a573bdb0a22332d913b0f44866df88eda10cf0e7e109bbc
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f914eda9eeb48dd88c7d72dc7b5a8e649d9d0ef052e83c4735837314c14189ff
+oid sha256:6b3bd421fa52c8e2b7dc9996a35f01475ce9c979f39176b33273b067935325fa
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764a6873ddb2313b79baf623bc05db7cfce490bcc328142b981cbe6e476af233
+oid sha256:663786479e3e2067e10a8ad17262c1bf863c2409883b4c5957bbc15345bc21c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.38691768050193787,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016181229773462782,
+  "best_metric": 0.35508111119270325,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.032362459546925564,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 24.141,
       "eval_steps_per_second": 3.023,
       "step": 25
+    },
+    {
+      "epoch": 0.016828478964401296,
+      "grad_norm": 5.934874057769775,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.2681,
+      "step": 26
+    },
+    {
+      "epoch": 0.017475728155339806,
+      "grad_norm": 5.760540008544922,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.3412,
+      "step": 27
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 5.337496280670166,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.2902,
+      "step": 28
+    },
+    {
+      "epoch": 0.018770226537216828,
+      "grad_norm": 5.112076759338379,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.1409,
+      "step": 29
+    },
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 5.294675827026367,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.1751,
+      "step": 30
+    },
+    {
+      "epoch": 0.020064724919093852,
+      "grad_norm": 5.933514595031738,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.3161,
+      "step": 31
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 6.715687274932861,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3662,
+      "step": 32
+    },
+    {
+      "epoch": 0.021359223300970873,
+      "grad_norm": 6.21199893951416,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.2211,
+      "step": 33
+    },
+    {
+      "epoch": 0.022006472491909384,
+      "grad_norm": 7.3447794914245605,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.4038,
+      "step": 34
+    },
+    {
+      "epoch": 0.022653721682847898,
+      "grad_norm": 6.385514259338379,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2576,
+      "step": 35
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 8.130139350891113,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.391,
+      "step": 36
+    },
+    {
+      "epoch": 0.02394822006472492,
+      "grad_norm": 7.305758953094482,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.2573,
+      "step": 37
+    },
+    {
+      "epoch": 0.02459546925566343,
+      "grad_norm": 7.050241470336914,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3572,
+      "step": 38
+    },
+    {
+      "epoch": 0.02524271844660194,
+      "grad_norm": 8.658832550048828,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5489,
+      "step": 39
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 7.916935920715332,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2835,
+      "step": 40
+    },
+    {
+      "epoch": 0.026537216828478965,
+      "grad_norm": 8.260157585144043,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2949,
+      "step": 41
+    },
+    {
+      "epoch": 0.027184466019417475,
+      "grad_norm": 7.884759902954102,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.1645,
+      "step": 42
+    },
+    {
+      "epoch": 0.027831715210355986,
+      "grad_norm": 10.152740478515625,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4604,
+      "step": 43
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 9.72319221496582,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4565,
+      "step": 44
+    },
+    {
+      "epoch": 0.02912621359223301,
+      "grad_norm": 11.225317001342773,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.53,
+      "step": 45
+    },
+    {
+      "epoch": 0.02977346278317152,
+      "grad_norm": 11.727689743041992,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3768,
+      "step": 46
+    },
+    {
+      "epoch": 0.030420711974110032,
+      "grad_norm": 17.733081817626953,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6249,
+      "step": 47
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 12.744095802307129,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.2594,
+      "step": 48
+    },
+    {
+      "epoch": 0.03171521035598705,
+      "grad_norm": 31.65728759765625,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.7199,
+      "step": 49
+    },
+    {
+      "epoch": 0.032362459546925564,
+      "grad_norm": 48.377784729003906,
+      "learning_rate": 0.0,
+      "loss": 1.8259,
+      "step": 50
+    },
+    {
+      "epoch": 0.032362459546925564,
+      "eval_loss": 0.35508111119270325,
+      "eval_runtime": 107.785,
+      "eval_samples_per_second": 24.15,
+      "eval_steps_per_second": 3.025,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.128611934155571e+16,
+  "total_flos": 3.917361458656051e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null